AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Curvature Generation in Curved Spaces for Few-Shot Learning

Zhi Gao, Yuwei Wu, Yunde Jia, Mehrtash Harandi

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 59 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add HAN with fixed c=1 to prototype averaging (ablation)Curvature generation FSL · mini-ImageNet 1-shot inductive, BigResNet12accuracy: 59.05 -> 62.60Improved
add CCG (class-level curvatures) on top of HAN (ablation)Curvature generation FSL · mini-ImageNet 1-shot inductive, BigResNet12accuracy: 62.60 -> 67.02Improved
generate class-level curvatures instead of a single curvature (ablation)Curvature generation FSL · mini-ImageNet 1-shot inductive, BigResNet12accuracy: 58.97 -> 59.47Improved
generate curvature (CCG) instead of fixed c=0.01 with HAN (ablation)Curvature generation FSL · mini-ImageNet 1-shot inductive, BigResNet12accuracy: 64.17 -> 67.02Improved
fixed curvature c=0.01 instead of c=1 without CCG and HAN (ablation)Prototype averaging · mini-ImageNet 1-shot inductive, BigResNet12accuracy: 59.05 -> 50.92Hurt
fixed curvature c=0.01 instead of c=1 with HAN (ablation)HAN · mini-ImageNet 1-shot inductive, BigResNet12 (5-shot)accuracy: 1-shot 62.60 -> 64.17; 5-shot 79.25 -> 76.49Mixed
increase m from 1 to 4 collected samples (ablation)HAN · mini-ImageNet 1-shot inductiveaccuracy: 65.03 -> 67.02Improved
increase m from 15 to 60 collected samples (ablation)HAN · mini-ImageNet 1-shot transductiveaccuracy: 65.88 -> 71.79Improved
increase m from 60 to 75 (ablation)HAN · mini-ImageNet 1-shot transductiveaccuracy: 71.79 -> 71.11No clear effect
full method vs model-capacity-matched variant (ablation)Curvature generation FSL · mini-ImageNet 1-shot transductive, BigResNet12accuracy: 68.25 -> 71.79Improved
generate curvature from second-order statistics instead of concatenation (ablation)CCG · mini-ImageNet 5-shot transductiveaccuracy: 82.04 -> 83.00Improved
generate curvature from second-order statistics instead of mean (ablation)CCG · mini-ImageNet 5-shot transductiveaccuracy: 80.73 -> 83.00Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy